Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    key terms indicating significance or novelty in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.80
    RenderAtEndOf
    -0.70
    UserScript
    -0.63
    ftagPool
    -0.58
     terraces
    -0.54
    utnik
    -0.52
    uxxxx
    -0.50
     paramInt
    -0.50
     or
    -0.49
    igshid
    -0.49
    POSITIVE LOGITS
    Denne
    0.69
     purpoſe
    0.61
     deste
    0.61
    EXCLUSIVE
    0.61
     tartalomajánló
    0.60
    bewerken
    0.60
     بهذا
    0.60
    Tento
    0.60
    Этот
    0.59
    چنین
    0.56
    Act Density 0.168%

    No Known Activations